Engineering Manager, GPU Kernel Lead – Inference

Neura Market; San Francisco, Northern (CA, KY); Hybrid; USD 230,000 - 320,000; Full time

Benefits offered by this job

Competitive equity

100% medical, dental, vision

Flexible PTO including Winter Break

Parental leave

Fertility stipend

401(k)

Learning opportunities

Job summary

Baseten is seeking an Engineering Manager to lead our GPU Kernel Engineering team, directing CUDA kernel work and GPU architecture optimization within Baseten's inference stack. This player-coach role combines hands-on coding with building processes, culture, and a roadmap for a world-class kernel team.

You'll collaborate with senior leaders to align kernel work with Baseten's broader strategy and guide engineers toward high-quality, high-impact results.

Qualifications

• Must have led a GPU/ML systems team and hired/developed engineers
• Deep hands-on CUDA kernel experience in production
• Strong understanding of GPU memory hierarchy, warps, and tensor cores
• Experience with NVIDIA Hopper/Blackwell and CUDA ecosystem

Responsibilities

• Lead, grow, and mentor a team of GPU kernel engineers
• Set technical direction for the kernel roadmap and balance short-term and long-term goals
• Collaborate with Chief Scientist and VP Engineering to align with Baseten's inference stack
• Drive cross-functional collaboration with Model Performance, Capacity, and Infrastructure teams

Skills

People leadership

CUDA kernels

GPU architecture

NVIDIA CUDA ecosystem

Profiling tools

Technical direction

Tools

Nsight Systems

Nsight Compute

Torch Profiler

Triton

CUTLASS

CuTe DSL

Job description

Baseten is seeking an Engineering Manager to lead our GPU Kernel Engineering team, directing CUDA kernel work and GPU architecture optimization within Baseten's inference stack. This player-coach role combines hands-on coding with building processes, culture, and a roadmap for a world-class kernel team.

You'll collaborate with senior leaders to align kernel work with Baseten's broader strategy and guide engineers toward high-quality, high-impact results.